A Contemporary Survey of Large Language Model Assisted Program Analysis
It addresses the need for comprehensive reviews on LLMs in program analysis to guide security researchers in enhancing detection frameworks, but it is incremental as it synthesizes existing studies without new results.
This survey systematically reviews the application of Large Language Models (LLMs) in program analysis, categorizing work into static, dynamic, and hybrid approaches, and identifies future directions and challenges to advance the field.
The increasing complexity of software systems has driven significant advancements in program analysis, as traditional methods unable to meet the demands of modern software development. To address these limitations, deep learning techniques, particularly Large Language Models (LLMs), have gained attention due to their context-aware capabilities in code comprehension. Recognizing the potential of LLMs, researchers have extensively explored their application in program analysis since their introduction. Despite existing surveys on LLM applications in cybersecurity, comprehensive reviews specifically addressing their role in program analysis remain scarce. In this survey, we systematically review the application of LLMs in program analysis, categorizing the existing work into static analysis, dynamic analysis, and hybrid approaches. Moreover, by examining and synthesizing recent studies, we identify future directions and challenges in the field. This survey aims to demonstrate the potential of LLMs in advancing program analysis practices and offer actionable insights for security researchers seeking to enhance detection frameworks or develop domain-specific models.